Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unken
    -0.07
     Cay
    -0.06
    	test
    -0.06
    스터
    -0.06
    amam
    -0.06
    TAB
    -0.06
    _RF
    -0.06
     Ragnar
    -0.06
     FML
    -0.06
     Lin
    -0.06
    POSITIVE LOGITS
    or
    0.07
    -secondary
    0.07
    WAYS
    0.07
    _voltage
    0.06
    umber
    0.06
    .option
    0.06
     unwitting
    0.06
    (private
    0.06
    Iterator
    0.06
    анія
    0.06
    Act Density 0.004%

    No Known Activations